© 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. 13017
    Prev
    Next
    INDEX
    Explanations

    phrases related to published content and media

    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
    690
    +0.13
    0.4%
    1343
    +0.12
    0.3%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1116
    +0.13
    0.04
    474
    +0.12
    0.03
    764
    +0.10
    0.04
    Negative Logits
    towane
    -0.60
    towany
    -0.56
     자신의
    -0.55
     leg
    -0.54
     port
    -0.53
     den
    -0.53
     silicate
    -0.52
     patatas
    -0.52
     le
    -0.52
     com
    -0.52
    POSITIVE LOGITS
     célé
    1.45
     vété
    1.36
     confé
    1.32
     télécharge
    1.32
     espé
    1.24
     balenciaga
    1.23
     déplo
    1.22
     cannes
    1.18
     gouver
    1.18
     rassemble
    1.15
    Activations Density 0.275%

    No Known Activations