© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7609
    Prev
    Next
    INDEX
    Explanations

    terms related to technical aspects and capabilities, particularly focusing on scalability, usability, and bioavailability

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.12
    0.4%
    1616
    +0.09
    0.3%
    1127
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1005
    +0.12
    0.06
    919
    +0.09
    0.03
    1220
    +0.08
    0.04
    Negative Logits
     mef
    -1.63
     embra
    -1.62
     emphat
    -1.58
     indestru
    -1.57
     philanth
    -1.55
     effe
    -1.54
     socie
    -1.53
     Mlle
    -1.53
     sappi
    -1.53
     Intere
    -1.53
    POSITIVE LOGITS
     issues
    0.67
     sustainability
    0.66
     reliability
    0.66
     of
    0.65
     compliance
    0.65
     stability
    0.62
     levels
    0.62
    IBILITY
    0.61
     compatibility
    0.61
     status
    0.61
    Activations Density 0.317%

    No Known Activations