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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 299
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific entity or brand

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1052
    +0.09
    0.3%
    1103
    +0.08
    0.2%
    130
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1340
    +0.09
    0.03
    78
    +0.08
    0.02
    690
    +0.07
    0.02
    Negative Logits
     fået
    -0.58
    ensaft
    -0.52
     hossz
    -0.52
     givet
    -0.52
     plads
    -0.51
    insertBefore
    -0.51
     JsonResult
    -0.50
    uerte
    -0.49
    aporation
    -0.49
     houten
    -0.49
    POSITIVE LOGITS
     Mob
    2.69
     mob
    2.55
    Mob
    2.53
     MOB
    2.17
    mob
    2.07
    MOB
    1.84
     Mobility
    1.79
     mobility
    1.78
     mobili
    1.76
    Mobility
    1.74
    Activations Density 0.222%

    No Known Activations