Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2757
    Prev
    Next
    INDEX
    Explanations

    names and terms related to legal proceedings and politics

    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
    1310
    +0.16
    0.6%
    241
    +0.14
    0.5%
    90
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1310
    +0.16
    0.03
    241
    +0.14
    0.03
    981
    +0.12
    0.03
    Negative Logits
    DataAnnotations
    -0.60
     Laufe
    -0.60
    Polizei
    -0.59
    CPtr
    -0.58
    spesies
    -0.57
    DeleteMapping
    -0.57
    getColumnIndex
    -0.55
    Detalhes
    -0.55
     Ξ
    -0.54
    OGND
    -0.53
    POSITIVE LOGITS
     ftu
    1.64
     fta
    1.53
     vns
    1.47
     ftre
    1.40
     »>
    1.40
     poff
    1.39
     reft
    1.38
     squa
    1.37
     thut
    1.37
     fuf
    1.35
    Activations Density 0.090%

    No Known Activations