© 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. 14148
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes, such as monitoring, tuning, and syncing

    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
    1013
    +0.14
    0.4%
    1870
    +0.11
    0.3%
    284
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.08
    1812
    +0.11
    0.05
    1142
    +0.08
    0.04
    Negative Logits
     emphat
    -1.24
     sappi
    -1.24
     dises
    -1.21
     specialmente
    -1.20
     purtroppo
    -1.19
     parteci
    -1.17
     revan
    -1.16
     mef
    -1.14
     Ottobre
    -1.14
     increa
    -1.12
    POSITIVE LOGITS
     by
    1.00
     via
    0.75
     as
    0.74
    by
    0.74
     through
    0.71
     in
    0.70
     during
    0.69
     according
    0.69
     with
    0.67
     into
    0.67
    Activations Density 0.463%

    No Known Activations