© 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. 13800
    Prev
    Next
    INDEX
    Explanations

    file directory paths and version numbers in a specific programming environment

    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
    1343
    +0.16
    0.5%
    453
    +0.15
    0.5%
    1224
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.04
    1224
    +0.15
    0.03
    453
    +0.13
    0.03
    Negative Logits
    <bos>
    -0.83
    Dichloroethene
    -0.80
    QMetaType
    -0.73
     ***!
    -0.72
    styleType
    -0.72
    principalTable
    -0.67
     Baillargeon
    -0.66
    Dichlorobenzene
    -0.66
    HasForeignKey
    -0.65
    Dichloropropane
    -0.65
    POSITIVE LOGITS
    fordable
    1.24
     volunte
    1.20
     practition
    1.19
     !...
    1.16
    arture
    1.15
     ?...
    1.14
     inol
    1.14
     peculi
    1.13
     pollut
    1.12
     affor
    1.11
    Activations Density 0.120%

    No Known Activations